Problem
Research questions and friction points this paper is trying to address.
image compression
wind turbines
region-of-interest
defect detection
high-resolution images
End-to-End Image Compression with Segmentation Guided Dual Coding for Wind Turbines
🤖 AI Summary
This study addresses the high transmission cost of high-resolution images in wind turbine inspection, where efficient compression is required without compromising critical details of blade regions. To this end, the work proposes the first end-to-end deep learning framework that jointly performs blade segmentation and dual-mode (lossy/lossless) compression. The method integrates CRF-regularized segmentation, hyperprior-based lossy encoding, and a parallel lossless bit-refinement mechanism, leveraging a BU-Netv2+P segmentation network, a hierarchical bit-refinement encoder, and a background bit reuse strategy. Evaluated on a large-scale wind turbine dataset, the proposed approach significantly outperforms existing techniques, achieving substantially improved compression efficiency while preserving defect detection accuracy.
📝 Abstract
Transferring large volumes of high-resolution images during wind turbine inspections introduces a bottleneck in assessing and detecting severe defects. Efficient coding must preserve high fidelity in blade regions while aggressively compressing the background. In this work, we propose an end-to-end deep learning framework that jointly performs segmentation and dual-mode (lossy and lossless) compression. The segmentation module accurately identifies the blade region, after which our region-of-interest (ROI) compressor encodes it at superior quality compared to the rest of the image. Unlike conventional ROI schemes that merely allocate more bits to salient areas, our framework integrates: (i) a robust segmentation network (BU-Netv2+P) with a CRF-regularized loss for precise blade localization, (ii) a hyperprior-based autoencoder optimized for lossy compression, and (iii) an extended bits-back coder with hierarchical models for fully lossless blade reconstruction. Furthermore, our ROI framework removes the sequential dependency in bits-back coding by reusing background-coded bits, enabling parallelized and efficient dual-mode compression. To the best of our knowledge, this is the first fully integrated learning-based ROI codec combining segmentation, lossy, and lossless compression, ensuring that subsequent defect detection is not compromised. Experiments on a large-scale wind turbine dataset demonstrate superior compression performance and efficiency, offering a practical solution for automated inspections.
Innovation
Methods, ideas, or system contributions that make the work stand out.
region-of-interest compression
semantic segmentation
dual-mode compression
bits-back coding
end-to-end learning
🔎 Similar Papers
No similar papers found.
